我要吃瓜

Citation

Ali L, Khelil K, Wajid S, Hussain ZU, Shah MA, Howard A, Adeel A, Shah AA, Sudhakar U, Howard N & Hussain A (2017) Machine learning based computer-aided diagnosis of liver tumours. In: Howard N, Wang Y, Hussain A, Widrow B & Zadeh L (eds.) 2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC). 2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC), Oxford, 26.07.2017-28.07.2017. Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers Inc. pp. 139-145. https://doi.org/10.1109/ICCI-CC.2017.8109742

Abstract
Image processing plays a vital role in the early detection and diagnosis of Hepatocellular Carcinoma (HCC). In this paper, we present a computational intelligence based Computer-Aided Diagnosis (CAD) system that helps medical specialists detect and diagnose HCC in its initial stages. The proposed CAD comprises the following stages: image enhancement, liver segmentation, feature extraction and characterization of HCC by means of classifiers. In the proposed CAD framework, a Discrete Wavelet Transform (DWT) based feature extraction and Support Vector Machine (SVM) based classification methods are introduced for HCC diagnosis. For training and testing, the recorded biomarkers and the associated imaging data are fused. The classification accuracy of the proposed system is critically analyzed and compared with state-of-the-art machine learning algorithms. In addition, laboratory biomarkers are also used to cross-validate the diagnosis.

Keywords
Support vector machines; Kernel; Feature extraction; Design automation; Image enhancement; Liver